The Wayback Machine - https://web.archive.org/web/20230713123322/https://github.com/huggingface/peft/issues
Skip to content

Issues: huggingface/peft

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

77 Open 342 Closed
77 Open 342 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇄1�7 + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Calling merge_and_unload then save_pretrained uploads weights twice
#692 opened Jul 13, 2023 by fozziethebeat
1 of 4 tasks
1
Can peft support timm style ViT model when using lora?
#691 opened Jul 13, 2023 by double-fire-0
3
tuning “shallow encoder and deep decoder 1�7 model
#689 opened Jul 12, 2023 by Zz-dong
2 of 4 tasks
Matrix mistmatch when trying to adapt Falcon with QLoRA, how to fix?
#685 opened Jul 11, 2023 by brando90
2 of 4 tasks
2
Vision question answering
#682 opened Jul 11, 2023 by ppyt
add lora bias even if the target.bias don't exist
#679 opened Jul 10, 2023 by LZY-the-boys
1
Is convert_peft_sd_lora_to_kohya_ss.py not quite suitable for SD 2.0?
#677 opened Jul 10, 2023 by Ted-developer
2
Expected GPU usage improvement
#675 opened Jul 9, 2023 by andrei-saceleanu
prompt-tuning/p-tuning with 'decoder_attention_mask' using PeftModelForSeq2SeqLM
#674 opened Jul 9, 2023 by cjl99
4 tasks done
GPT-2 fine-tuned with LoRA and trainable embedding and predicion head FAILED to be loaded and inference
#673 opened Jul 8, 2023 by zxh0916
2 of 4 tasks
doing qlora finetune with deepspeed
#671 opened Jul 7, 2023 by Nisoka
1
Progress bar merge_and_unload
#667 opened Jul 6, 2023 by BramVanroy
1
get_peft_model() changes the parameter names, with prefix: base_model.model
#666 opened Jul 5, 2023 by ndvbd
4 tasks
2
ValueError:You should supply an instance of transformers.BatchFeature or list of transformers.BatchFeature to this method that includes input_values, but you provided ['label']
#665 opened Jul 5, 2023 by fanOfJava
1
Not getting substantial training time improvement with LORA - is this expected ?
#664 opened Jul 5, 2023 by SuchandraDatta
3
Adalora: query_key_value.lora_B.default has been marked as ready twice
#663 opened Jul 5, 2023 by diaojunxian
2 of 4 tasks
3
whisper-peft model to onnx
#660 opened Jul 2, 2023 by marziye-A
1
Is it necessary to provide target_modules in LoraConfig?
#659 opened Jul 1, 2023 by siddhsql
1
High memory consumption during LORA training
#658 opened Jul 1, 2023 by DanielRoeder1
2 of 4 tasks
3
Multi-GPU use different amounts of memory in DDP with LoRA
#655 opened Jun 30, 2023 by sherdencooper
2
Prototype LoRA/Adapter/Prefix-tuning support - Arxiv PRs welcome to address this contributions are welcome from community members on this issue
#648 opened Jun 28, 2023 by he20010515
1
Adding weighted adapter as LoRAs combination gives unexpected result with StableDiffusion compared to webui
#643 opened Jun 27, 2023 by kovalexal
2 of 4 tasks
2
Merge LoRA Adapter with int8 base model.
#638 opened Jun 26, 2023 by jenkspt
9
gradients cannot propagate correctly on the cloned lora model
#634 opened Jun 26, 2023 by luguangyao
2 of 4 tasks
Anyone using triton python backend?
#633 opened Jun 26, 2023 by YooSungHyun
3 of 4 tasks
9
ProTip! Find all open issues with in progress development work with linked:pr.